The geo-mcp server provides OSM-backed multimodal (walk + transit) navigation and geospatial tools for LLM applications without proprietary map APIs.
Geocoding & Reverse Geocoding: Convert place names/addresses to coordinates (geocode) and coordinates to human-readable locations (reverse_geocode).
Multimodal Route Planning: Plan walk + transit routes with adaptive strategies (A* for short trips, hierarchical transit-skeleton for longer journeys) and optional deferred processing (plan_route).
Area Loading & Caching: Load and cache OSM walk and transit graph data for a place or bounding box, enabling offline/local processing and faster queries (load_area).
Points of Interest Discovery: Find nearby OSM POIs such as cafes, pharmacies, and parks by category and radius (find_nearby).
Transit Options Lookup: List nearby transit stops and the lines serving them (list_transit_options).
Area Description: Get a structured summary of an area's major roads, neighborhoods, and landmarks for geographic context (describe_area).
Network Snapping: Snap coordinates to the nearest graph node (intersection or transit stop) for precise routing (snap_to_network).
Asynchronous Job Management: Submit, check, cancel, and list background jobs for long routing tasks (submit_route, get_job, cancel_job, list_jobs).
Offline Operation & Resilient Data Handling: Operate offline after initial OSM ingestion; uses retries, circuit breakers, and deadlines for online operations.
Provides tools for geocoding, routing, and exploring points of interest using OpenStreetMap data, enabling multimodal (walking and transit) navigation.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@geo-mcp Plan a walking route from Central Park to Times Square"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OSM-backed multimodal (walk + transit) navigation MCP server. Gives LLM apps structured routing and geo tools for any distance — neighborhood walks to cross-city transit — without proprietary map APIs.
Offline / local PBF: download a Geofabrik extract once (geo-mcp ingest), then route without Overpass
Distance-adaptive routing: local multimodal A* for short trips; hierarchical transit-skeleton + walk access/egress for long ones
Tiled parallel loads: walk/transit graphs from local clips or Overpass tiles
Deferred jobs + progress: long routes can return job_id; poll with get_job
Resilient OSM I/O: retries, circuit breakers, deadlines (online mode)
Transports: stdio (default) and optional Streamable HTTP
Related MCP server: Geo MCP Worker
Tool | Purpose |
| Place ↔ coordinates |
| Adaptive multimodal route (optional |
| Always-background route job |
| Job lifecycle |
| Prefetch tiles for explore/ |
| Nearby OSM POIs |
| Nearby stops and lines |
| Major roads, neighborhoods, landmarks |
| Nearest graph node (auto-loads a local tile if needed) |
Python 3.14+
For offline clipping: osmium-tool (brew install osmium-tool)
cd /path/to/geo-mcp
uv sync
brew install osmium-tool # once, for offline bbox extractsDownload once, then never hit Overpass for routing:
# ~300–400 MB for Île-de-france
uv run geo-mcp ingest --region ile-de-france
uv run geo-mcp status
# Serve MCP offline
GEO_MCP_OFFLINE=true uv run geo-mcpCursor env example: set GEO_MCP_OFFLINE=true and GEO_MCP_PBF_REGION=ile-de-france. Other regions: berlin, greater-london, france. Or pass --url for any .osm.pbf.
# Cursor / Claude Desktop (stdio)
uv run geo-mcp
# Optional Streamable HTTP
uv run geo-mcp --transport streamable-http --host 127.0.0.1 --port 8000
# Verbose logs
uv run geo-mcp --log-level INFO{
"mcpServers": {
"geo-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/geo-mcp",
"run",
"geo-mcp"
],
"env": {
"PYTHONWARNINGS": "ignore"
}
}
}
}geocode origin and destination
plan_route with coordinates (no prior load_area required)
If the response has job_id, poll get_job until status is completed (or failed)
Optionally describe_area / find_nearby after a local load_area
uv run pytestLive OSM smoke (needs network):
uv run python scripts/smoke_route.pyEnvironment variables use the GEO_MCP_ prefix. Important knobs:
Variable | Default | Meaning |
|
| Never call Overpass; require local PBF/cache |
|
| Geofabrik region for ingest |
| — | Explicit path to |
|
| Use local PBF when present |
|
| Below this → local A*; above → hierarchical |
|
| Access/egress stop search radius |
|
| Walk tile grid size (~1 km) |
|
| Parallel tile workers |
|
| Soft sync budget (long trips auto-defer) |
|
| Hard deadline per route/load |
|
| Retries per Overpass endpoint |
|
| Disk graph cache |
src/geo_mcp/
domain/ # geo, network, pathfinding, hierarchical router
application/ # use cases, job service, DTOs
infrastructure/
resilience/ # retry, circuit breaker, deadline
graph/ # disk cache + tile store
osm/ # Nominatim, Overpass, OSMnx repository
interfaces/mcp/ # FastMCP tools (+ progress)Transit uses OSM topology and heuristic speeds (not GTFS realtime schedules)
Hierarchical routing stitches transit with walk tiles / geodesic walk fallbacks at the ends
First fetch for uncached tiles still depends on Overpass/OSMnx latency
Map data © OpenStreetMap contributors
Respect Nominatim usage policy and Overpass etiquette
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for Japan geodata: cadastral lot numbers (chiban) and reverse geocoding, for AI agents.
MCP server for Mireye Earth — federal-source-cited geospatial data for any MCP-aware agent.
OpenStreetMap Overpass MCP — programmatic queries against the OSM database
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/FaresKi/geo-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server